The Spiral Discovery Network as an Automated General-Purpose Optimization Tool. (12th March 2018)
- Record Type:
- Journal Article
- Title:
- The Spiral Discovery Network as an Automated General-Purpose Optimization Tool. (12th March 2018)
- Main Title:
- The Spiral Discovery Network as an Automated General-Purpose Optimization Tool
- Authors:
- Csapo, Adam B.
- Other Names:
- Wong Kevin Academic Editor.
- Abstract:
- Abstract : The Spiral Discovery Method (SDM) was originally proposed as a cognitive artifact for dealing with black-box models that are dependent on multiple inputs with nonlinear and/or multiplicative interaction effects. Besides directly helping to identify functional patterns in such systems, SDM also simplifies their control through its characteristic spiral structure. In this paper, a neural network-based formulation of SDM is proposed together with a set of automatic update rules that makes it suitable for both semiautomated and automated forms of optimization. The behavior of the generalized SDM model, referred to as the Spiral Discovery Network (SDN), and its applicability to nondifferentiable nonconvex optimization problems are elucidated through simulation. Based on the simulation, the case is made that its applicability would be worth investigating in all areas where the default approach of gradient-based backpropagation is used today.
- Is Part Of:
- Complexity. Volume 2018(2018)
- Journal:
- Complexity
- Issue:
- Volume 2018(2018)
- Issue Display:
- Volume 2018, Issue 2018 (2018)
- Year:
- 2018
- Volume:
- 2018
- Issue:
- 2018
- Issue Sort Value:
- 2018-2018-2018-0000
- Page Start:
- Page End:
- Publication Date:
- 2018-03-12
- Subjects:
- Chaotic behavior in systems -- Periodicals
Complexity (Philosophy) -- Periodicals
003 - Journal URLs:
- https://onlinelibrary.wiley.com/journal/10990526 ↗
http://onlinelibrary.wiley.com/ ↗
https://www.hindawi.com/journals/complexity/ ↗ - DOI:
- 10.1155/2018/1947250 ↗
- Languages:
- English
- ISSNs:
- 1076-2787
- Deposit Type:
- Legaldeposit
- View Content:
- Available online (eLD content is only available in our Reading Rooms) ↗
- Physical Locations:
- British Library DSC - 3364.585500
British Library HMNTS - ELD Digital store - Ingest File:
- 22602.xml